Methods and apparatus to generate physical therapy exercise profiles

Abstract

Systems, apparatus, articles of manufacture, and methods are disclosed to generate physical therapy exercise profiles. An example non-transitory machine readable storage medium comprising instructions to cause programmable circuitry to at least: obtain, via a user interface, an indication of a characteristic for an exercise; obtain, via the user interface, a video depicting a person performing the exercise; analyze, using a machine learning algorithm, the video to detect a body position and a movement of the person performing the exercise; and cause an exercise profile to be stored for the exercise, the exercise profile including the indication of the characteristic for the exercise, an identification of the body position, and an identification of the movement.

What is claimed is: 
     
         1 . A non-transitory machine readable storage medium comprising instructions to cause programmable circuitry to at least:
 obtain, via a user interface, an indication of a characteristic for an exercise;   obtain, via the user interface, a video depicting a person performing the exercise;   analyze, using a machine learning algorithm, the video to detect a body position and a movement of the person performing the exercise; and   cause an exercise profile to be stored for the exercise, the exercise profile including the indication of the characteristic for the exercise, an identification of the body position, and an identification of the movement.   
     
     
         2 . The non-transitory machine readable medium of  claim 1 , wherein the characteristic is a body position of the person depicted in the video. 
     
     
         3 . The non-transitory machine readable medium of  claim 1 , wherein the instructions, when executed, cause the programmable circuitry to present the exercise to a user. 
     
     
         4 . The non-transitory machine readable medium of  claim 3 , wherein the instructions, when executed, cause the machine to:
 obtain a second video of an exercise participant performing the exercise;   analyze, using the machine learning algorithm, the second video to determine metadata of the exercise participant performing the exercise;   compare the metadata to the exercise profile; and   present an indication of the comparison via a graphical user interface.   
     
     
         5 . The non-transitory machine readable medium of  claim 1 , wherein the instructions, when executed, cause the programmable circuitry to analyze, using the machine learning algorithm, the video to determine a starting partition for the exercise. 
     
     
         6 . The non-transitory machine readable medium of  claim 1 , wherein the instructions, when executed, cause the programmable circuitry to:
 obtain, via the user interface, a plurality of videos depicting the person performing the exercise; and   analyze, using the machine learning algorithm, the plurality of videos to detect the body position and the movement of the person performing the exercise.   
     
     
         7 . The non-transitory machine readable medium of  claim 1 , wherein the instructions, when executed, cause the programmable circuitry to present a second user interface to obtain a modified to the exercise profile. 
     
     
         8 . An apparatus comprising:
 machine readable instructions; and   programmable circuitry to at least one of instantiate or execute the machine readable instructions to:
 obtain, via a user interface, an indication of a characteristic for an exercise; 
 obtain, via the user interface, a video depicting a person performing the exercise; 
 analyze, using a machine learning algorithm, the video to detect a body position and a movement of the person performing the exercise; and 
 cause an exercise profile to be stored for the exercise, the exercise profile including the indication of the characteristic for the exercise, an identification of the body position, and an identification of the movement. 
   
     
     
         9 . The apparatus of  claim 8 , wherein the characteristic is a body position of the person depicted in the video. 
     
     
         10 . The apparatus of  claim 8 , wherein the programmable circuitry is to present the exercise to a user. 
     
     
         11 . The apparatus of  claim 10 , wherein the programmable circuitry is to:
 obtain a second video of an exercise participant performing the exercise;   analyze, using the machine learning algorithm, the second video to determine metadata of the exercise participant performing the exercise;   compare the metadata to the exercise profile; and   present an indication of the comparison via a graphical user interface.   
     
     
         12 . The apparatus of  claim 8 , wherein the programmable circuitry is to analyze, using the machine learning algorithm, the video to determine a starting partition for the exercise. 
     
     
         13 . The apparatus of  claim 8 , wherein the programmable circuitry is to:
 obtain, via the user interface, a plurality of videos depicting the person performing the exercise; and   analyze, using the machine learning algorithm, the plurality of videos to detect the body position and the movement of the person performing the exercise.   
     
     
         14 . The apparatus of  claim 8 , wherein the programmable circuitry is to present a second user interface to obtain a modified to the exercise profile. 
     
     
         15 . A method comprising:
 obtaining, via a user interface, an indication of a characteristic for an exercise;   obtaining, via the user interface, a video depicting a person performing the exercise;   analyzing, using a machine learning algorithm, the video to detect a body position and a movement of the person performing the exercise; and   causing an exercise profile to be stored for the exercise, the exercise profile including the indication of the characteristic for the exercise, an identification of the body position, and an identification of the movement.   
     
     
         16 . The method of  claim 15 , wherein the characteristic is a body position of the person depicted in the video. 
     
     
         17 . The method of  claim 15 , further comprising presenting the exercise to a user. 
     
     
         18 . The method of  claim 17 , further comprising:
 obtaining a second video of an exercise participant performing the exercise;   analyzing, using the machine learning algorithm, the second video to determine metadata of the exercise participant performing the exercise;   comparing the metadata to the exercise profile; and   presenting an indication of the comparison via a graphical user interface.   
     
     
         19 . The method of  claim 15 , further comprising analyzing, using the machine learning algorithm, the video to determine a starting partition for the exercise. 
     
     
         20 . The method of  claim 15 , further comprising:
 obtaining, via the user interface, a plurality of videos depicting the person performing the exercise; and   analyzing, using the machine learning algorithm, the plurality of videos to detect the body position and the movement of the person performing the exercise.